© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94009
    Prev
    Next
    INDEX
    Explanations

    body parts and movement

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spotlights words describing foot‐related movements or directions (e.g. step, left, right, back, behind, foot, heel).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Handball
    -0.91
     wrists
    -0.80
    手で
    -0.77
     sluit
    -0.75
     ética
    -0.74
    (|
    -0.74
     rượu
    -0.73
    ֙
    -0.73
     Naidu
    -0.72
    люби
    -0.69
    POSITIVE LOGITS
     foot
    4.31
    foot
    3.02
     Foot
    2.95
    Foot
    2.86
     FOOT
    2.48
    FOOT
    2.20
     feet
    2.16
     leg
    1.84
     Fuß
    1.84
     piede
    1.73
    Activations Density 0.030%

    No Known Activations